TY  - JOUR
A1  - Magunia, Harry
A1  - Lederer, Simone
A1  - Verbuecheln, Raphael
A1  - Gilot, Bryant Joseph
A1  - Koeppen, Michael
A1  - Haeberle, Helene A.
A1  - Mirakaj, Valbona
A1  - Hofmann, Pascal
A1  - Marx, Gernot
A1  - Bickenbach, Johannes
A1  - Nohe, Boris
A1  - Lay, Michael
A1  - Spies, Claudia
A1  - Edel, Andreas
A1  - Schiefenhövel, Fridtjof
A1  - Rahmel, Tim
A1  - Putensen, Christian
A1  - Sellmann, Timur
A1  - Koch, Thea
A1  - Brandenburger, Timo
A1  - Kindgen-Milles, Detlef
A1  - Brenner, Thorsten
A1  - Berger, Marc
A1  - Zacharowski, Kai
A1  - Adam, Elisabeth
A1  - Posch, Matthias
A1  - Moerer, Onnen
A1  - Scheer, Christian S.
A1  - Sedding, Daniel
A1  - Weigand, Markus A.
A1  - Fichtner, Falk
A1  - Nau, Carla
A1  - Prätsch, Florian
A1  - Wiesmann, Thomas
A1  - Koch, Christian
A1  - Schneider, Gerhard
A1  - Lahmer, Tobias
A1  - Straub, Andreas
A1  - Meiser, Andreas
A1  - Weiss, Manfred
A1  - Jungwirth, Bettina
A1  - Wappler, Frank
A1  - Meybohm, Patrick
A1  - Herrmann, Johannes
A1  - Malek, Nisar
A1  - Kohlbacher, Oliver
A1  - Biergans, Stephanie
A1  - Rosenberger, Peter
T1  - Machine learning identifies ICU outcome predictors in a multicenter COVID-19 cohort
T2  - Critical Care
N2  - Background
Intensive Care Resources are heavily utilized during the COVID-19 pandemic. However, risk stratification and prediction of SARS-CoV-2 patient clinical outcomes upon ICU admission remain inadequate. This study aimed to develop a machine learning model, based on retrospective & prospective clinical data, to stratify patient risk and predict ICU survival and outcomes.

Methods
A Germany-wide electronic registry was established to pseudonymously collect admission, therapeutic and discharge information of SARS-CoV-2 ICU patients retrospectively and prospectively. Machine learning approaches were evaluated for the accuracy and interpretability of predictions. The Explainable Boosting Machine approach was selected as the most suitable method. Individual, non-linear shape functions for predictive parameters and parameter interactions are reported.

Results
1039 patients were included in the Explainable Boosting Machine model, 596 patients retrospectively collected, and 443 patients prospectively collected. The model for prediction of general ICU outcome was shown to be more reliable to predict “survival”. Age, inflammatory and thrombotic activity, and severity of ARDS at ICU admission were shown to be predictive of ICU survival. Patients’ age, pulmonary dysfunction and transfer from an external institution were predictors for ECMO therapy. The interaction of patient age with D-dimer levels on admission and creatinine levels with SOFA score without GCS were predictors for renal replacement therapy.

Conclusions
Using Explainable Boosting Machine analysis, we confirmed and weighed previously reported and identified novel predictors for outcome in critically ill COVID-19 patients. Using this strategy, predictive modeling of COVID-19 ICU patient outcomes can be performed overcoming the limitations of linear regression models.

Trial registration “ClinicalTrials” (clinicaltrials.gov) under NCT04455451.
KW  - COVID-19
KW  - critical care
KW  - ARDS
KW  - outcome
KW  - prognostic models
Y1  - 2021
UR  - https://opus.bibliothek.uni-wuerzburg.de/opus4-wuerzburg/frontdoor/index/index/docId/30676
UR  - https://nbn-resolving.org/urn:nbn:de:bvb:20-opus-306766
VL  - 25
ER  -